feedsvc: Neo4j queries per request 15.6 — 3.9× the fleet's usual 4.0
info
Service outlier
master
open
impact 15
opened 7d ago · last observed 1d ago · observed 392× · #17066 · b97af412dc572868e356
What happened template
feedsvc's Neo4j queries per request is 15.6 against the 7 other services' median of 4.0 (4.4 robust MADs above, six-hour window). This compares the service with its peers, not with its own history — the seasonal detector does that.
A service unlike the rest of the fleet on one measure (robust z against its peers).
The facts
| measures | {'measure': 'Neo4j queries per request', 'value': 15.574074074074074, 'value_fmt': '15.6', 'median': 3.9773371104815864, 'median_fmt': '4.0', 'mad': 2.642312195121951, 'z': 4.388859493969546, 'direction': 'above', 'peers': 7} |
| measure | Neo4j queries per request |
| value | 15.57 |
| value_fmt | 15.6 |
| median | 3.98 |
| median_fmt | 4.0 |
| z | 4.39 |
| direction | above |
| peers | 7 |
| rule | {"min_score": 3.5, "min_relative_pct": 35, "warn_on": []} |
| discriminator | |
| window | 2026-11-16 23:43:34 UTC → 2026-11-17 05:43:34 UTC |
What is failing in feedsvc — the bad events, decomposed
“Bad events” are HTTP 5xx answers from feedsvc. In this finding's window (2026-11-16 23:43:34 UTC → 2026-11-17 05:43:34 UTC) there were 0; every line links to the grouped errors behind it.
The error shapes behind them
| 3× | Unable to retrieve routing information since 2026-11-12 13:44:27 UTC |
History
Check it yourself
Every link carries the finding's own time window, so it shows tomorrow what it shows now.
Actions
Sign in (IAP) to acknowledge, snooze or resolve.
Where the numbers come from
| source | rollup |
| collected_at | 1794894089 |
| age_seconds | 125 |
| stale | False |
| shown | None |
| total | None |
| truncated | False |
| coverage_from | None |
| retain_days | None |
| note | None |
| detector | outliers |